mlsanityData to 14 Oct 2026

AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection

arXiv 2505.12594 ↗First posted 19 May 2025cs.CL cs.AIcited by 8

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for non-expert users who lack in-depth library-specific knowledge and advanced programming skills. To tackle this, we present AD-AGENT, an LLM-driven multi-agent framework that turns natural-language instructions into fully executable AD pipelines. AD-AGENT coordinates specialized agents for intent parsing, data preparation, library and model selection, documentation mining, and iterative code generation and debugging. Using a shared short-term workspace and a long-term cache, the agents integrate popular AD libraries like PyOD, PyGOD, and TSLib into a unified workflow. Experiments demonstrate that AD-AGENT produces reliable scripts and recommends competitive models across libraries. The system is open-sourced to support further research and practical applications in AD.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 16 of its 31 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

16 of 31 references.

References · 16

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  4. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  5. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  6. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
  7. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  8. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 178
  9. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  10. 2024Large Language Model Agent for Hyper-Parameter Optimizationcited by 64
  11. 2024ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agentscited by 36
  12. 2022PyGOD: A Python Library for Graph Outlier Detectioncited by 32
4 more
  1. 2025Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Modelscited by 19
  2. 2024PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selectioncited by 17
  3. 2024MetaOOD: Automatic Selection of OOD Detection Modelscited by 16
  4. 2025Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  2. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 14
  3. 2026Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Biascited by 3
  4. 2026LLM Agents for Time-Series: A Surveycited by 1
  5. 2026Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activitycited by 0
  6. 2026Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detectioncited by 0
  7. 2026Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifierscited by 0
  8. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
  2. 2025LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
  3. 2026AgenticTwin: An Agentic LLM Framework Integrated with Digital Twin for Anomaly Detection
  4. 2025TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
  5. 2026Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages
  6. 2026CHASE: LLM Agents for Dissecting Malicious PyPI Packages
  7. 2026Multi-Agent Debate: A Unified Agentic Framework for Tabular Anomaly Detection
  8. 2025SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems